Skip to Main content Skip to Navigation

Neural architectures for estimating correspondences between images

Abstract : The goal of this thesis is to develop methods for establishing correspondences between pairs of images in challenging situations, such as extreme illumination changes, scenes with little texture or with repetitive structures, and matching parts of objects which belong to the same class, but which may have large intra-class appearance differences. In summary, our contributions are the following: (i) we develop a trainable approach for parametric image alignment by means of a siamese network model, (ii) we devise a weakly-supervised training approach, which allows training from real image pairs having only annotation at the level of image-pairs, (iii) we propose the Neighbourhood Consensus Networks which can be used to robustly estimate correspondences in tasks where discrete correspondences are required, and (iv) because the dense formulation of the Neighbourhood Consensus Networks is memory and computationally intensive, we develop a more efficient variant that can reduce the memory requirements and run-time by more than ten times.
Complete list of metadata
Contributor : Ignacio Rocco Connect in order to contact the contributor
Submitted on : Sunday, December 27, 2020 - 10:44:58 AM
Last modification on : Friday, January 21, 2022 - 3:16:39 AM
Long-term archiving on: : Monday, March 29, 2021 - 6:37:45 PM


Files produced by the author(s)


  • HAL Id : tel-03088795, version 1



Ignacio Rocco. Neural architectures for estimating correspondences between images. Computer Vision and Pattern Recognition [cs.CV]. École Normale Supérieure, 2020. English. ⟨tel-03088795⟩



Les métriques sont temporairement indisponibles